Moving shadows detection in video sequences

Video surveillance and traffic monitoring systems can be heavily improved using vision-based techniques that able to detect manage, and track objects in the field of view. However, problems arise due to shadows can affect the correct localization and detection of moving objects. This paper aims to present a method for detecting shadows that accompany moving objects. The proposed method is based on three sources of information. First, shadows are attached their respective objects. Second, a region covers by shadow in current frame is always darker than the same region in background frame. Finally, the ratio between current and background pixels are roughly constant under shadow regions. The proposed method can be exploited in a system for moving visual object detection to improve detection accuracy. The experimental results on real video sequences show the effectiveness of this method.